© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62659
    Prev
    Next
    INDEX
    Explanations

    charset, Indian, Q, Political

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     satisfe
    -0.97
    ("</
    -0.88
    getSystem
    -0.87
    ябре
    -0.85
    fahrer
    -0.82
    ailles
    -0.80
    exión
    -0.80
    ственном
    -0.79
    :</
    -0.79
    ícula
    -0.79
    POSITIVE LOGITS
    캉
    0.76
     terrors
    0.74
     unknow
    0.72
     포함
    0.72
    ūd
    0.71
    品種
    0.71
     pres
    0.69
     monotony
    0.69
    Buildings
    0.68
     Beds
    0.68
    Activations Density 0.013%

    No Known Activations